in models/rexnetv1.py [0:0]
def __init__(self):
super().__init__()
self.features_0 = torch.nn.modules.conv.Conv2d(3, 32, (3, 3), stride=(2, 2), padding=(1, 1), dilation=(1, 1), bias=False)
self.features_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self.features_3_out_0 = torch.nn.modules.conv.Conv2d(32, 32, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=32, bias=False)
self.features_3_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self.features_3_out_2 = torch.nn.modules.activation.ReLU6()
self.features_3_out_3 = torch.nn.modules.conv.Conv2d(32, 16, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_3_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self.features_4_out_0 = torch.nn.modules.conv.Conv2d(16, 96, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_4_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(96)
self.features_4_out_3 = torch.nn.modules.conv.Conv2d(96, 96, (3, 3), stride=(2, 2), padding=(1, 1), dilation=(1, 1), groups=96, bias=False)
self.features_4_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(96)
self.features_4_out_5 = torch.nn.modules.activation.ReLU6()
self.features_4_out_6 = torch.nn.modules.conv.Conv2d(96, 27, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_4_out_7 = torch.nn.modules.batchnorm.BatchNorm2d(27)
self.features_5_out_0 = torch.nn.modules.conv.Conv2d(27, 162, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_5_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(162)
self.features_5_out_3 = torch.nn.modules.conv.Conv2d(162, 162, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=162, bias=False)
self.features_5_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(162)
self.features_5_out_5 = torch.nn.modules.activation.ReLU6()
self.features_5_out_6 = torch.nn.modules.conv.Conv2d(162, 38, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_5_out_7 = torch.nn.modules.batchnorm.BatchNorm2d(38)
self.features_6_out_0 = torch.nn.modules.conv.Conv2d(38, 228, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_6_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(228)
self.features_6_out_3 = torch.nn.modules.conv.Conv2d(228, 228, (3, 3), stride=(2, 2), padding=(1, 1), dilation=(1, 1), groups=228, bias=False)
self.features_6_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(228)
self.features_6_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_6_out_5_fc_0 = torch.nn.modules.conv.Conv2d(228, 19, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_6_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(19)
self.features_6_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_6_out_5_fc_3 = torch.nn.modules.conv.Conv2d(19, 228, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_6_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_6_out_6 = torch.nn.modules.activation.ReLU6()
self.features_6_out_7 = torch.nn.modules.conv.Conv2d(228, 50, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_6_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(50)
self.features_7_out_0 = torch.nn.modules.conv.Conv2d(50, 300, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_7_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(300)
self.features_7_out_3 = torch.nn.modules.conv.Conv2d(300, 300, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=300, bias=False)
self.features_7_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(300)
self.features_7_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_7_out_5_fc_0 = torch.nn.modules.conv.Conv2d(300, 25, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_7_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(25)
self.features_7_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_7_out_5_fc_3 = torch.nn.modules.conv.Conv2d(25, 300, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_7_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_7_out_6 = torch.nn.modules.activation.ReLU6()
self.features_7_out_7 = torch.nn.modules.conv.Conv2d(300, 61, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_7_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(61)
self.features_8_out_0 = torch.nn.modules.conv.Conv2d(61, 366, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_8_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(366)
self.features_8_out_3 = torch.nn.modules.conv.Conv2d(366, 366, (3, 3), stride=(2, 2), padding=(1, 1), dilation=(1, 1), groups=366, bias=False)
self.features_8_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(366)
self.features_8_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_8_out_5_fc_0 = torch.nn.modules.conv.Conv2d(366, 30, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_8_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(30)
self.features_8_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_8_out_5_fc_3 = torch.nn.modules.conv.Conv2d(30, 366, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_8_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_8_out_6 = torch.nn.modules.activation.ReLU6()
self.features_8_out_7 = torch.nn.modules.conv.Conv2d(366, 72, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_8_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(72)
self.features_9_out_0 = torch.nn.modules.conv.Conv2d(72, 432, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_9_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(432)
self.features_9_out_3 = torch.nn.modules.conv.Conv2d(432, 432, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=432, bias=False)
self.features_9_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(432)
self.features_9_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_9_out_5_fc_0 = torch.nn.modules.conv.Conv2d(432, 36, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_9_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(36)
self.features_9_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_9_out_5_fc_3 = torch.nn.modules.conv.Conv2d(36, 432, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_9_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_9_out_6 = torch.nn.modules.activation.ReLU6()
self.features_9_out_7 = torch.nn.modules.conv.Conv2d(432, 84, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_9_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(84)
self.features_10_out_0 = torch.nn.modules.conv.Conv2d(84, 504, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_10_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(504)
self.features_10_out_3 = torch.nn.modules.conv.Conv2d(504, 504, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=504, bias=False)
self.features_10_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(504)
self.features_10_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_10_out_5_fc_0 = torch.nn.modules.conv.Conv2d(504, 42, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_10_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(42)
self.features_10_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_10_out_5_fc_3 = torch.nn.modules.conv.Conv2d(42, 504, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_10_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_10_out_6 = torch.nn.modules.activation.ReLU6()
self.features_10_out_7 = torch.nn.modules.conv.Conv2d(504, 95, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_10_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(95)
self.features_11_out_0 = torch.nn.modules.conv.Conv2d(95, 570, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_11_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(570)
self.features_11_out_3 = torch.nn.modules.conv.Conv2d(570, 570, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=570, bias=False)
self.features_11_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(570)
self.features_11_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_11_out_5_fc_0 = torch.nn.modules.conv.Conv2d(570, 47, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_11_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(47)
self.features_11_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_11_out_5_fc_3 = torch.nn.modules.conv.Conv2d(47, 570, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_11_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_11_out_6 = torch.nn.modules.activation.ReLU6()
self.features_11_out_7 = torch.nn.modules.conv.Conv2d(570, 106, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_11_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(106)
self.features_12_out_0 = torch.nn.modules.conv.Conv2d(106, 636, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_12_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(636)
self.features_12_out_3 = torch.nn.modules.conv.Conv2d(636, 636, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=636, bias=False)
self.features_12_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(636)
self.features_12_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_12_out_5_fc_0 = torch.nn.modules.conv.Conv2d(636, 53, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_12_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(53)
self.features_12_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_12_out_5_fc_3 = torch.nn.modules.conv.Conv2d(53, 636, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_12_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_12_out_6 = torch.nn.modules.activation.ReLU6()
self.features_12_out_7 = torch.nn.modules.conv.Conv2d(636, 117, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_12_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(117)
self.features_13_out_0 = torch.nn.modules.conv.Conv2d(117, 702, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_13_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(702)
self.features_13_out_3 = torch.nn.modules.conv.Conv2d(702, 702, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=702, bias=False)
self.features_13_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(702)
self.features_13_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_13_out_5_fc_0 = torch.nn.modules.conv.Conv2d(702, 58, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_13_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(58)
self.features_13_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_13_out_5_fc_3 = torch.nn.modules.conv.Conv2d(58, 702, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_13_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_13_out_6 = torch.nn.modules.activation.ReLU6()
self.features_13_out_7 = torch.nn.modules.conv.Conv2d(702, 128, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_13_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(128)
self.features_14_out_0 = torch.nn.modules.conv.Conv2d(128, 768, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_14_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(768)
self.features_14_out_3 = torch.nn.modules.conv.Conv2d(768, 768, (3, 3), stride=(2, 2), padding=(1, 1), dilation=(1, 1), groups=768, bias=False)
self.features_14_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(768)
self.features_14_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_14_out_5_fc_0 = torch.nn.modules.conv.Conv2d(768, 64, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_14_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self.features_14_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_14_out_5_fc_3 = torch.nn.modules.conv.Conv2d(64, 768, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_14_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_14_out_6 = torch.nn.modules.activation.ReLU6()
self.features_14_out_7 = torch.nn.modules.conv.Conv2d(768, 140, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_14_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(140)
self.features_15_out_0 = torch.nn.modules.conv.Conv2d(140, 840, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_15_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(840)
self.features_15_out_3 = torch.nn.modules.conv.Conv2d(840, 840, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=840, bias=False)
self.features_15_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(840)
self.features_15_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_15_out_5_fc_0 = torch.nn.modules.conv.Conv2d(840, 70, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_15_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(70)
self.features_15_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_15_out_5_fc_3 = torch.nn.modules.conv.Conv2d(70, 840, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_15_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_15_out_6 = torch.nn.modules.activation.ReLU6()
self.features_15_out_7 = torch.nn.modules.conv.Conv2d(840, 151, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_15_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(151)
self.features_16_out_0 = torch.nn.modules.conv.Conv2d(151, 906, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_16_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(906)
self.features_16_out_3 = torch.nn.modules.conv.Conv2d(906, 906, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=906, bias=False)
self.features_16_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(906)
self.features_16_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_16_out_5_fc_0 = torch.nn.modules.conv.Conv2d(906, 75, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_16_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(75)
self.features_16_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_16_out_5_fc_3 = torch.nn.modules.conv.Conv2d(75, 906, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_16_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_16_out_6 = torch.nn.modules.activation.ReLU6()
self.features_16_out_7 = torch.nn.modules.conv.Conv2d(906, 162, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_16_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(162)
self.features_17_out_0 = torch.nn.modules.conv.Conv2d(162, 972, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_17_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(972)
self.features_17_out_3 = torch.nn.modules.conv.Conv2d(972, 972, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=972, bias=False)
self.features_17_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(972)
self.features_17_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_17_out_5_fc_0 = torch.nn.modules.conv.Conv2d(972, 81, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_17_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(81)
self.features_17_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_17_out_5_fc_3 = torch.nn.modules.conv.Conv2d(81, 972, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_17_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_17_out_6 = torch.nn.modules.activation.ReLU6()
self.features_17_out_7 = torch.nn.modules.conv.Conv2d(972, 174, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_17_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(174)
self.features_18_out_0 = torch.nn.modules.conv.Conv2d(174, 1044, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_18_out_1 = torch.nn.modules.batchnorm.BatchNorm2d(1044)
self.features_18_out_3 = torch.nn.modules.conv.Conv2d(1044, 1044, (3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=1044, bias=False)
self.features_18_out_4 = torch.nn.modules.batchnorm.BatchNorm2d(1044)
self.features_18_out_5_avg_pool = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.features_18_out_5_fc_0 = torch.nn.modules.conv.Conv2d(1044, 87, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_18_out_5_fc_1 = torch.nn.modules.batchnorm.BatchNorm2d(87)
self.features_18_out_5_fc_2 = torch.nn.modules.activation.ReLU(inplace=True)
self.features_18_out_5_fc_3 = torch.nn.modules.conv.Conv2d(87, 1044, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))
self.features_18_out_5_fc_4 = torch.nn.modules.activation.Sigmoid()
self.features_18_out_6 = torch.nn.modules.activation.ReLU6()
self.features_18_out_7 = torch.nn.modules.conv.Conv2d(1044, 185, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_18_out_8 = torch.nn.modules.batchnorm.BatchNorm2d(185)
self.features_19 = torch.nn.modules.conv.Conv2d(185, 1280, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1), bias=False)
self.features_20 = torch.nn.modules.batchnorm.BatchNorm2d(1280)
self.features_22 = torch.nn.modules.pooling.AdaptiveAvgPool2d(1)
self.output_0 = torch.nn.modules.dropout.Dropout(p=0.2)
self.output_1 = torch.nn.modules.conv.Conv2d(1280, 1000, (1, 1), stride=(1, 1), padding=(0, 0), dilation=(1, 1))